Deepstream deployment of yolov3 does not produce detection boxes

[18981275647]

Please provide complete information as applicable to your setup.

**• Hardware Platform (Jetson / GPU) jetson tx2
**• DeepStream Version6
**• JetPack Version (valid for Jetson only) 4.6

When I deploy my own yolov3 trained model using deep flow, I can generate the inference engine but cannot get the bounding box. I modified the paresbbox file of yolov3 according to the introduction on the official website. How to deal with it?

[AastaLLL]

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

Hi,

Do you apply the customization mentioned in the document below:
https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_custom_YOLO.html

The guidance is for the model retrained with Darknet.
Do you also have .cfg and .weight format via deep flow?

Thanks.